INDEX

Explanations

references to animals, specifically sheep

oai_token-act-pair · gpt-3.5-turbo

references to sheep and related terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

entric

-0.71

ENTS

-0.69

arcity

-0.69

 validity

-0.68

 GOODMAN

-0.66

 eminent

-0.66

 vehement

-0.65

 devast

-0.64

 undue

-0.61

rylic

-0.61

POSITIVE LOGITS

ishly

1.02

 sheep

1.00

dog

0.92

dogs

0.90

skin

0.89

itte

0.85

poke

0.84

pei

0.79

meat

0.79

erness

0.77

Activations Density 0.005%

references to animals, specifically sheep

references to sheep and related terms

No Comments

No Known Activations